Micro-service-based power grid health degree sensing method and system

Abstract

The invention discloses a micro-service-based power grid health degree sensing method and system, and relates to the technical field of power grid health sensing, and the method comprises the steps: carrying out the data collection, and transmitting the data to a data processing center; performing first analysis on the data, and evaluating the health degree; and performing fault location based on the first perception. According to the micro-service-based power grid health degree sensing method provided by the invention, the system can quickly carry out fault analysis from multiple dimensions through triggering of the first sensing, and the specific position and reason of the fault are determined. The quick response capability can greatly shorten the fault processing time and reduce the influence of the fault on the operation of the power grid. The containerization deployment mode of the acquisition nodes enables the system to efficiently adapt to different power grid environments, including virtualization and containerization platforms, so that the system is ensured to stably operate in various complex computing environments, and the requirements of various environments are met. The method has better effects in the aspects of reliability, accuracy and applicability.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid health perception, and in particular to a microservice-based power grid health perception method and system. Background Art

[0002] As the scale of modern power systems continues to expand and the structure becomes increasingly complex, the safe and stable operation of power grids faces unprecedented challenges. Traditional power grid monitoring methods mainly rely on centralized architectures, with limited data collection and processing capabilities, making it difficult to respond to dynamically changing power loads and fault conditions in a timely manner. In recent years, the application of microservice architectures and big data processing technologies in power systems has gradually emerged. The high scalability and flexibility of microservices can be used to monitor and manage power grid equipment in a refined manner. At the same time, the development of streaming and batch processing technologies provides technical support for real-time analysis of massive power grid operation data, making real-time monitoring of power grid status and health assessment possible.

[0003] However, the existing power grid monitoring and health assessment technologies still have many shortcomings. First, the data collection method is relatively single, and it is impossible to fully obtain the multi-dimensional data of power grid equipment, especially in different operating environments and equipment types, and there is a lack of flexible collection mechanism. Secondly, the data transmission and processing efficiency is low, which makes it difficult to meet the needs of large-scale power systems for real-time data analysis, resulting in delayed monitoring of the power grid status. Thirdly, the existing fault diagnosis methods usually rely on a single data source, lack of comprehensive analysis of inter-device communication, network traffic and call relationships, and it is difficult to locate the fault point in a timely and accurate manner. In addition, in the face of the complexity and diversity of the power grid, the traditional system lacks efficient scalability and environmental adaptability, and cannot meet the needs of modern power grids for flexible deployment and dynamic expansion. Therefore, there is an urgent need for a microservice-based power grid health perception method that can achieve multi-level data collection, efficient data transmission and real-time fault diagnosis to improve the operation safety and reliability of the power grid. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is that the existing power grid monitoring method has the problems of incomplete data collection, insufficient real-time analysis capability and difficulty in quickly and accurately locating faults.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: a microservice-based power grid health perception method, comprising collecting data and transmitting the data to a data processing center; performing a first analysis on the data to evaluate the health; and locating the fault based on the first perception.

[0007] As a preferred solution of the microservice-based power grid health perception method described in the present invention, wherein: the multi-level data collection includes configuring nodes to perform multi-level data collection.

[0008] As a preferred solution of the microservice-based power grid health perception method described in the present invention, the data transmission to the data processing center includes real-time data transmission and synchronous preliminary aggregation.

[0009] As a preferred solution of the microservice-based power grid health perception method described in the present invention, the first analysis of the data includes analyzing the data after preliminary aggregation and outputting performance indicators.

[0010] As a preferred solution of the microservice-based power grid health perception method described in the present invention, wherein: the health evaluation includes evaluating the health of the power grid system through a model.

[0011] As a preferred solution of the microservice-based grid health perception method described in the present invention, the fault location based on the first perception includes triggering the first perception when the system detects that the health of the grid equipment has declined, and locating the fault based on the first perception.

[0012] As a preferred solution of the microservice-based power grid health perception method described in the present invention, the fault location based on the first perception also includes generating a fault analysis report and a fault location report and sending them to the operation and maintenance personnel. After the operation and maintenance personnel complete the repair, they input the specific cause of the fault and the maintenance strategy, and the system stores the fault cause and maintenance strategy corresponding to the positioning point.

[0013] Another object of the present invention is to provide a microservice-based power grid health perception system, which can obtain the real-time status of equipment operation through multi-level data collection, help to timely discover potential problems, improve the safety and reliability of power grid operation, and solve the problem of incomplete data collection in current power grid monitoring methods.

[0014] As a preferred solution of the microservice-based power grid health perception system described in the present invention, it includes: a data acquisition module, a data analysis module, and a fault perception module; the data acquisition module is used to collect data and transmit the data to a data processing center; the data analysis module is used to perform a first analysis on the data and evaluate the health; the fault perception module is used to locate the fault based on the first perception.

[0015] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement a method for realizing a microservice-based power grid health awareness.

[0016] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a microservice-based power grid health perception method.

[0017] Beneficial effects of the present invention: The microservice-based grid health perception method provided by the present invention is triggered by the first perception, and the system can quickly perform fault analysis from multiple dimensions to determine the specific location and cause of the fault. This rapid response capability can significantly shorten the fault handling time and reduce the impact of the fault on the operation of the grid. The containerized deployment of the acquisition node enables it to efficiently adapt to different grid environments, including virtualization and containerized platforms, ensuring that the system can operate stably in various complex computing environments and meet the needs of multiple environments. The present invention achieves better results in terms of reliability, accuracy and applicability. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0019] Figure 1 An overall flow chart of a microservice-based grid health perception method provided for the first embodiment of the present invention.

[0020] Figure 2 An overall flow chart of a microservice-based power grid health perception system provided in the third embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0022] Example 1, reference Figure 1 , is an embodiment of the present invention, and provides a microservice-based power grid health perception method, including:

[0023] S1: collect data and transmit data to the data processing center;

[0024] Furthermore, performing multi-level data collection includes configuring nodes to perform multi-level data collection.

[0025] It should be noted that in order to adapt to different power grid environments, the collection nodes are deployed in containers, which have efficient scalability and flexibility. Collection nodes are installed on different devices in the power grid, such as transformers, circuit breakers, protection relays, etc. Each collection node runs independently and can collect data such as voltage, current, frequency, power, etc. of the equipment in real time. The collection node supports running in virtual machines and container environments, such as KVM hosts, K8s nodes, etc., to ensure that the system can adapt to various environments of the Southern Power Grid Cloud Platform.

[0026] In order to achieve efficient monitoring of the entire power grid, the system implements two types of data collection mechanisms: horizontal and vertical.

[0027] Horizontal collection: Horizontal collection is mainly used to monitor the key performance indicators of equipment in the power grid, such as current, voltage, frequency, etc. These data can reflect the immediate working status of the equipment and provide basic data for subsequent health scores.

[0028] Vertical collection: Vertical collection is used to monitor the communication links, network traffic, device call relationships, etc. between power grid devices. By analyzing the data at the network layer and application layer vertically, the system can better understand the dependencies between devices and quickly locate the problem when a link failure occurs.

[0029] In addition to collecting device performance data, the system also needs to collect network traffic between devices to perform link analysis when a fault occurs.

[0030] In a virtualized environment, the collector can collect traffic data of all virtual machines on the KVM host through an independent user-mode process running on the host.

[0031] In the container environment, the collection node is deployed on the K8s node in the form of DaemonSet, which is responsible for collecting traffic data of POD, NAT conversion network port, and node network port.

[0032] The system also supports parsing traffic encapsulated in tunnels such as VXLAN and GRE to ensure complete monitoring of the container network.

[0033] Furthermore, data transmission to the data processing center includes real-time data transmission and simultaneous preliminary aggregation. After data collection is completed, the system transmits the data from the collection node to the central processing system through an efficient transmission mechanism. In order to cope with the data volume of the large-scale power system of the Southern Power Grid, the system uses high-throughput message queue tools such as Kafka.

[0034] Through the Kafka message middleware, the system can efficiently transmit data collected by different devices and different network nodes to the central processing platform.

[0035] In addition to device performance data, the system also supports the transmission of various log data such as network traffic logs, HTTP logs, DNS logs, etc. It can help the system track device behavior and analyze abnormal situations.

[0036] The data transmitted to the central processing system needs to be further preprocessed and aggregated to ensure the efficiency and accuracy of subsequent analysis.

[0037] The system aggregates the collected data preliminarily according to the type of power grid equipment, the network environment in which the equipment is located, and the link characteristics. For example, network traffic, equipment performance data, and log data are aggregated into different data pools.

[0038] The traffic collector is used to extract and uniformly store the traffic logs of the physical network, virtual network, and container network to generate network topology data for subsequent link analysis.

[0039] S2: Perform the first analysis of the data and evaluate the healthiness;

[0040] Furthermore, the first analysis of the data includes analyzing the data after preliminary aggregation and outputting performance indicators.

[0041] The first analysis of the data may be performed in a variety of analysis methods, such as data analysis based on a stream processing framework, periodic data analysis based on batch processing, or other data processing methods that can adapt to the complexity of the power grid.

[0042] As a preferred embodiment, in this embodiment, the first analysis adopts data analysis based on the streaming processing framework, and uses the Flink streaming processing engine to analyze the operating data and network flow data of the power grid equipment in real time. The streaming processing engine can process massive data streams to achieve real-time monitoring and anomaly detection of the power grid status. The specific steps are: based on the performance indicators such as current, voltage, frequency, etc. collected by the equipment, the system can calculate the real-time status of the equipment, such as power fluctuations, load changes, etc. The system combines historical data to establish a baseline for each device, and automatically generates an exception report when the performance indicators of a certain device exceed the normal range. The collected log data is parsed, and abnormal log events are identified through methods such as log keyword matching and log volume fluctuation detection.

[0043] In order to fully control the operation status of the power grid, the system has a rich built-in indicator model library through knowledge graphs and indicator model libraries, which can display network layer, transmission layer, and flow path attribute data of different granularities. For example, it can display the number of collection points, the number of collectors, and the types of server ports of a certain node.

[0044] In another feasible embodiment, the first analysis adopts periodic data analysis based on batch processing, and the specific method is: through the batch processing framework Hadoop, the system regularly performs in-depth analysis on the accumulated large-scale data, generates trend reports and long-term performance evaluation. Perform long-term power grid health monitoring. The system regularly summarizes a large amount of historical operation data from various power grid collection points and stores it in a distributed file system or data warehouse. At the end of each cycle, the system performs a unified analysis of these historical data through the batch processing framework, and compares the historical trends and real-time collected data to evaluate the indicators.

[0045] It should be noted that it supports end-to-end network performance diagnosis between different devices in the power grid system, and can track fault points step by step from the physical level to the virtual machine and container level, realizing hop-by-hop analysis and link troubleshooting.

[0046] Furthermore, health evaluation includes evaluating the health of the power grid system through models. The model selection is based on anomaly detection models based on machine learning. The health score is mainly based on data such as equipment operating performance, log records, and alarm history. The scoring results are color-coded (such as red, yellow, and green) to intuitively display the health status of power grid equipment.

[0047] S3: Fault location based on first perception.

[0048] Furthermore, when the system detects that the health of the power grid equipment has declined, the first perception is triggered and the fault is located based on the first perception.

[0049] It should be noted that the first perception can adopt a variety of fault analysis and positioning methods, such as fault diagnosis based on call chain analysis, fault diagnosis based on network traffic analysis, or other fault judgment and positioning methods that can adapt to the complexity of the power grid and can accurately locate.

[0050] As a preferred embodiment, in this embodiment, the first perception adopts fault diagnosis based on call chain analysis, using the call chain tracking mechanism in the microservice system to track the path of the fault through trace_id and span_id technology to determine the source of the fault. Based on the call relationship between services, the fault point can be quickly and accurately located, and root cause analysis can be provided.

[0051] In another feasible embodiment, the first perception adopts fault diagnosis based on network traffic analysis, by monitoring the network traffic and communication links between the nodes of the power grid, analyzing abnormal phenomena such as traffic fluctuations, packet loss and delay, to diagnose the fault. This method locates the fault point in the power grid by analyzing abnormal data at the network level.

[0052] It should also be noted that a fault analysis report and a fault location report are generated and sent to the operation and maintenance personnel. After the operation and maintenance personnel complete the repair, they enter the specific cause of the fault and the maintenance strategy. The system stores the fault cause and maintenance strategy corresponding to the location point.

[0053] Example 2, an embodiment of the present invention, provides a microservice-based power grid health perception method. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0054] First, in order to verify the effectiveness of the proposed multi-level data acquisition and fault diagnosis system in the power grid environment, an experimental platform simulating a smart grid was established. The platform includes common power grid equipment such as transformers, circuit breakers, and protection relays. Collection nodes implemented by containerization technology are deployed on each device to ensure efficient scalability and flexibility in different power grid environments. The collection nodes are configured to run independently and can collect key operating parameters such as voltage, current, frequency, and power of the equipment in real time. These nodes are deployed on multiple platforms including KVM hosts and Kubernetes (K8s) nodes to simulate the diverse computing environments in modern power systems and ensure that the experimental objects are similar to the complex environment of the Southern Power Grid Cloud Platform.

[0055] Table 1 Experimental data comparison table

[0056] parameter Device A Device B Device C Equipment D Equipment E Equipment F Equipment G Voltage (V) 230 231 229 232 230 231 230 Current (A) 15 14.5 15.2 14.8 15.1 14.9 15 Frequency (Hz) 50 50 50 50 50 50 50 Power (kW) 3.45 3.35 3.48 3.43 3.47 3.44 3.45 Health score 95 92 96 93 94 95 90 Fault detection time(s) 2 2 2 2 2 2 5 Fault Location correct correct correct correct correct correct mistake

[0057] Through the data analysis of the above table, it can be seen that the multi-level data acquisition and fault diagnosis system (device AF) of the present invention has significant advantages over the traditional method (device G). First, in the monitoring of key performance indicators such as voltage and current, the data of device AF is highly consistent with the expected nominal values, indicating that the system can accurately collect the operating parameters of the equipment in real time to ensure the safe and stable operation of the power grid. The frequency index is maintained at 50Hz on all devices, reflecting the stability of the power grid operation, which is a basic requirement for ensuring power quality.

[0058] In terms of health score, the score of device AF is between 92 and 96, which is significantly higher than the 90 of device G. This shows that the machine learning anomaly detection model used in this system is more sensitive and accurate, and can comprehensively evaluate the multi-dimensional data of the equipment, timely discover potential operation risks, and provide a reliable basis for preventive maintenance.

[0059] In terms of fault detection time, the devices AF and G take 2 seconds, which is much faster than the 5 seconds of device G. This improvement in detection speed is due to the real-time data analysis capabilities of the streaming processing framework. In power grid operation, rapid fault detection is crucial to prevent accidents from expanding and ensure power supply continuity. Rapid fault detection can buy valuable processing time for operation and maintenance personnel and reduce the impact of faults on the power grid.

[0060] Fault location is an important indicator for evaluating the system's diagnostic capability. The system is basically capable of performing the location task.

[0061] Example 3, reference Figure 2 , as an embodiment of the present invention, provides a microservice-based power grid health perception system, including a data acquisition module, a data analysis module, and a fault perception module.

[0062] Among them, the data acquisition module is used to collect data and transmit the data to the data processing center; the data analysis module is used to perform a first analysis on the data and evaluate the health; and the fault perception module is used to locate the fault based on the first perception.

[0063] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0064] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0065] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0066] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc. It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and are not limited. Although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

[0067] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A microservice-based power grid health perception method, characterized in that: include: Collect data and transmit data to the data processing center; Conduct a first analysis of the data to evaluate health; Fault location based on first perception.

2. The microservice-based power grid health perception method according to claim 1, characterized in that: The multi-level data collection includes configuring nodes to perform multi-level data collection.

3. The microservice-based power grid health perception method according to claim 2, characterized in that: The transmitting of data to the data processing center includes real-time data transmission and simultaneous preliminary aggregation.

4. The microservice-based power grid health perception method according to claim 3, characterized in that: The first analysis of the data includes analyzing the data after preliminary aggregation and outputting performance indicators.

5. The microservice-based power grid health perception method according to claim 4, characterized in that: The health evaluation includes evaluating the health of the power grid system through a model.

6. The microservice-based power grid health perception method according to claim 5, characterized in that: The fault location based on the first perception includes triggering the first perception when the system detects that the health of the power grid equipment has declined, and performing fault location based on the first perception.

7. The microservice-based power grid health perception method according to claim 6, characterized in that: The fault location based on the first perception also includes generating a fault analysis report and a fault location report and sending them to the operation and maintenance personnel. After the operation and maintenance personnel complete the repair, they input the specific cause of the fault and the maintenance strategy. The system stores the fault cause and maintenance strategy corresponding to the positioning point.

8. A system using the microservice-based power grid health perception method according to any one of claims 1 to 7, characterized in that: Including data acquisition module, data analysis module, fault perception module; The data acquisition module is used to collect data and transmit the data to a data processing center; The data analysis module is used to perform a first analysis on the data to evaluate the health; The fault perception module is used to locate the fault based on the first perception.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the microservice-based grid health awareness method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the microservice-based grid health awareness method according to any one of claims 1 to 7 are implemented.

Images